Related papers: Command-line Obfuscation Detection using Small Lan…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Obfuscating compilers protect a software by obscuring its meaning and impeding the reconstruction of its original source code. The typical concern when defining such compilers is their robustness against reverse engineering and the…

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Anomaly detection is a method for discovering unusual and suspicious behavior. In many real-world scenarios, the examined events can be directly linked to the actions of an adversary, such as attacks on computer networks or frauds in…

Machine-learning techniques are widely used in security-related applications, like spam and malware detection. However, in such settings, they have been shown to be vulnerable to adversarial attacks, including the deliberate manipulation of…

Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs, have not yet been adopted by ML developers. We initiate…

Large Language Models (LLMs) have significantly advanced code analysis tasks, yet they struggle to detect malicious behaviors fragmented across files, whose intricate dependencies easily get lost in the vast amount of benign code. We…

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density…

Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…

With the increasingly rapid development of new malicious computer software by bad faith actors, both commercial and research-oriented antivirus detectors have come to make greater use of machine learning tactics to identify such malware as…

The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a…

Training AI models in cybersecurity with help of vast datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models…

Virtualization-based obfuscation produces extremely large and structurally complex binaries, posing challenges for LLM-based analysis due to input size limits and the need for large-scale labeled data. We address this by focusing on…

Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substitute for heavyweight cryptography in privacy-preserving…

As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…

With the continuous rise of malicious campaigns and the exploitation of new attack vectors, it is necessary to assess the efficacy of the defensive mechanisms used to detect them. To this end, the contribution of our work is twofold. First,…

Simple fine-tuning can embed hidden text into large language models (LLMs), which is revealed only when triggered by a specific query. Applications include LLM fingerprinting, where a unique identifier is embedded to verify licensing…

The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…

Current malware detection and classification approaches generally rely on time consuming and knowledge intensive processes to extract patterns (signatures) and behaviors from malware, which are then used for identification. Moreover, these…

Command injection vulnerabilities are a significant security threat in dynamic languages like Python, particularly in widely used open-source projects where security issues can have extensive impact. With the proven effectiveness of Large…